Rye supervision workbench

Wrap agents

Launch Claude Code, Codex CLI, and other coding assistants through Rye so traffic, policy, and audit events are connected.

Start free trial View pricing

Why wrapping matters

AI coding agents read environment variables, load local configuration, open files, run commands, and call model APIs. Wrapping starts the agent under Rye supervision from process launch time, when proxy variables and trust settings matter most.

Wrap common CLIs

Start Claude Code through Rye:

exec:bash

rye wrap claude

Start Codex CLI through Rye:

exec:bash

rye wrap codex

You can also install app shims for repeated use:

exec:bash

rye app wrap claude

exec:bash

rye app wrap codex

The install script already creates these shims when the tools are present. If you install an agent later, run rye app wrap for it.

Shims live in ~/.rye/shims. That directory must precede the real agent executable on PATH. Open a new terminal after installation, or update the current shell:

exec:bash

export PATH="$HOME/.rye/shims:$PATH"

After PATH is updated, the normal claude or codex command starts under Rye supervision. Proxy and CA environment variables are injected into the wrapped process and inherited by its children.

Inspect or disable shims

exec:bash

rye app list
rye app doctor

Remove wrapping for an app:

exec:bash

rye app unwrap claude codex

To skip shims during installation:

exec:bash

curl -fsSL https://barn.rye.ai/install.sh | sh -s -- --no-wrap-agents

Unwrapping removes the shim; it does not uninstall the agent or stop the Rye daemon.

Verify traffic

Use:

exec:bash

rye history --last 1h

exec:bash

rye status

You should see recent model traffic, process attribution, device identity, and policy decisions.

What wrapping does not do

Wrapping does not replace the agent's own permission model. Claude Code, Codex, Cursor, and other tools may still ask for local approvals. Rye sits outside those controls and gives the organization a separate enforcement and audit path.